text model · Granite · macOS
Can I run Granite 4.0 H Small on Apple M5 (32GB)?
Yes. Granite 4.0 H Small runs on Apple M5 (32GB) at Q4_K_M (~20.4 GB of ~21 GB usable).
Fits at Q4_K_M (~20.4 GB of ~21 GB usable) but with little headroom, close other apps.
- Q4_K_M needed
- ~20.4 GB
- Usable on device
- ~21 GB
- Device memory
- 32 GB
- Best quant
- Q4_K_M
Run it
Pick your tool. All three load the same Q4_K_M weights.
ollama run granite4:small-h llama-cli -hf unsloth/granite-4.0-h-small-GGUF:Q4_K_M lms get unsloth/granite-4.0-h-small-GGUF vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.
- Parameters
- 32B (MoE, 9B active)
- Q4_K_M size
- 18.23 GB
- Q8_0 size
- 31.91 GB
- Context
- 128k
- Ollama tag
- granite4:small-h
- Memory
- 32 GB unified
- Usable for weights
- ~21 GB
- Best runtime
- MLX direct / Ollama (MLX backend)
You could also run
Run Granite 4.0 H Small on other hardware
FAQ
Can Apple M5 (32GB) run Granite 4.0 H Small?
Yes. Granite 4.0 H Small runs on Apple M5 (32GB) at Q4_K_M (~20.4 GB of ~21 GB usable).
How much memory does Granite 4.0 H Small need?
It is a tight fit on Apple M5 (32GB). At Q4_K_M the weights are ~18.23 GB; with KV cache and runtime overhead, budget ~20.4 GB at a 4k context. It is a Mixture-of-Experts model (32B total / 9B active), so all experts must stay in memory; memory tracks total params, not active params.
What is the best tool to run Granite 4.0 H Small on macOS?
LM Studio for a simple setup; mlx-lm for the most speed. vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.
Sources
Memory figures are estimates. See methodology.